Pith. sign in

REVIEW 2 cited by

CodeFusion: A Pre-trained Diffusion Model for Code Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.17680 v3 pith:POPNEWBU submitted 2023-10-26 cs.SE cs.AIcs.CLcs.PL

Mukul Singh , José Cambronero , Sumit Gulwani , Vu Le , Carina Negreanu , Gust Verbruggen This is my paper · ORCID
classification cs.SEcs.AIcs.CLcs.PL
keywords codecodefusiongenerationlanguagenaturalaccuracyauto-regressivediffusion
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar limitation: they do not easily allow reconsidering earlier tokens generated. We introduce CodeFusion, a pre-trained diffusion code generation model that addresses this limitation by iteratively denoising a complete program conditioned on the encoded natural language. We evaluate CodeFusion on the task of natural language to code generation for Bash, Python, and Microsoft Excel conditional formatting (CF) rules. Experiments show that CodeFusion (75M parameters) performs on par with state-of-the-art auto-regressive systems (350M-175B parameters) in top-1 accuracy and outperforms them in top-3 and top-5 accuracy due to its better balance in diversity versus quality.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints

    cs.LG 2025-01 conditional novelty 6.0 of 10

    DART, a single-step embedding-space perturber trained with reinforcement learning, finds toxic prompts closer to reference prompts than fine-tuned or few-shot baselines on three LLMs.

  2. A Novel Diffusion Model for Pairwise Geoscience Data Generation with Unbalanced Training Dataset

    cs.LG 2025-01 conditional novelty 6.0 of 10

    UB-Diff generates paired velocity maps and seismic waveforms from unbalanced data using a shared latent space plus a two-step training scheme, and reports better FID and downstream inversion scores than prior methods.

Pith tools